The　alighting　and　boarding　behavior　of　passengers　at　the　subway　station　can　directly　affect　the　dwell　time　of　trains,　and　then　affect　the　service　level　of　stations.　The　HPO-BP　prediction　model　for　the　alighting　and　boarding　time　in　scenarios　with　different　types　of　waiting　areas　is　proposed　in　this　paper.　The　number　of　passengers,　gender,　whether　to　carry　luggage　or　children,　and　the　degree　of　passenger　civilization　are　selected　as　the　main　influence　factors　after　analyzing　the　data　of　field　investigations,　which　are　defined　as　the　input　variables　of　the　prediction　model.　The　alighting　and　boarding　time　is　defined　as　the　output　variable.　The　HPO-BP　prediction　model　is　trained,　tested　and　validated　by　using　the　data　collected　in　the　field　investigations.　The　comparison　results　indicate　that　the　prediction　accuracies　of　the　proposed　model　in　a　single　waiting　area　and　double　waiting　areas　are　35.8%　and　62.8%　higher　than　that　of　the　BP　neural　network,　and　are　also　significantly　improved　compared　with　other　advanced　algorithms.　It　can　be　concluded　that　the　gender　of　passengers　is　the　most　important　factor　affecting　passengers＇　alighting　and　boarding　time　after　the　interpretation　and　analysis　of　the　SHAP　model.　Moreover,　the　degree　of　passenger　civilization　also　has　a　certain　impact　on　the　alighting　and　boarding　efficiency.